註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Antigma
@antigma_labs
building substrate for self-organizing intelligence.
加入 July 2024
16 正在關注    933 粉絲
We just completely reworked our compaction algorithm to fit models with limited context window. it is much more reliable and intelligent. Perfect for - Local models - Frontier models with super long running uninterrupted tasks (we tested a case with 90 compactions and 500+ steps)
顯示更多